US20050234324A1 - Image display control apparatus and method, and program for controlling image display control apparatus - Google Patents
Image display control apparatus and method, and program for controlling image display control apparatus Download PDFInfo
- Publication number
- US20050234324A1 US20050234324A1 US11/089,225 US8922505A US2005234324A1 US 20050234324 A1 US20050234324 A1 US 20050234324A1 US 8922505 A US8922505 A US 8922505A US 2005234324 A1 US2005234324 A1 US 2005234324A1
- Authority
- US
- United States
- Prior art keywords
- image
- angle
- interest
- rotation correction
- rotated
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims description 11
- 238000011156 evaluation Methods 0.000 claims abstract description 116
- 230000001815 facial effect Effects 0.000 claims abstract description 58
- 238000001514 detection method Methods 0.000 claims description 48
- 238000004364 calculation method Methods 0.000 claims description 21
- 238000006243 chemical reaction Methods 0.000 claims description 12
- 238000013500 data storage Methods 0.000 claims description 2
- 230000001276 controlling effect Effects 0.000 description 11
- 239000000470 constituent Substances 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000002596 correlated effect Effects 0.000 description 1
- 230000000875 corresponding effect Effects 0.000 description 1
- 238000013144 data compression Methods 0.000 description 1
- 108091008695 photoreceptors Proteins 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/24—Aligning, centring, orientation detection or correction of the image
- G06V10/242—Aligning, centring, orientation detection or correction of the image by image rotation, e.g. by 90 degrees
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/61—Control of cameras or camera modules based on recognised objects
- H04N23/611—Control of cameras or camera modules based on recognised objects where the recognised objects include parts of the human body
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/63—Control of cameras or camera modules by using electronic viewfinders
Definitions
- This invention relates to an image display control apparatus and method and to a program for controlling the image display control apparatus.
- the camera When the image of a subject is sensed using a digital still camera or the like, generally the camera is held so as to be suitable for a landscape-type display. However, a camera is not always held so as to be suitable for a landscape display and there are instances where a camera is held so as to be suitable for a portrait-type display. In a case where the image is displayed, however, generally the set-up is such that the image is displayed in the landscape-type format. In order to display in portrait format an image that has been captured in the portrait format, therefore, it is necessary to designate the image and rotate it in such a manner that it will be displayed in the landscape format.
- an object of the present invention is to discriminate the orientation of an image and rotate the image upon rotating it in a direction suitable for the display.
- an image display control apparatus comprising in-area-image rotating means for rotating an image, which is located within a search area contained in an image of interest, through a specified angle in prescribed angular increments; evaluation-value calculating means for calculating an evaluation value, which represents facial likeliness of an image within the search area at each angle through which the image has been rotated in the prescribed angular increments by the in-area-image rotating means, using detection data for detecting a face image; rotation correction angle deciding means for deciding a rotation correction angle based upon an angle that affords a maximum value of the evaluation value representing facial likeliness at each angle by the evaluation-value calculating means; and display control means for controlling a display unit, in such a manner that the image of interest is rotated and displayed in a display window, using the rotation correction angle decided by the rotation correction angle deciding means.
- the first aspect of the present invention also provides a method suited to the above-described image display control apparatus. More specifically, the first aspect of the present invention provides an image display method comprising the steps of rotating an image, which is located within a search area contained in an image of interest, through a specified angle in prescribed angular increments; calculating an evaluation value, which represents facial likeliness of an image within the search area at each angle through which the image has been rotated in the prescribed angular increments, using detection data for detecting a face image; deciding a rotation correction angle based upon an angle that affords a maximum value of the evaluation value representing facial likeliness at each angle; and controlling a display unit, in such a manner that the image of interest is rotated and displayed in a display window, using the rotation correction angle decided.
- the first aspect of the present invention also provides a program for controlling the above-described image display control apparatus.
- an image within a search area that is included in an image of interest to be displayed (the size of the search area may be smaller than or the same as the size of the image of interest) is rotated in prescribed angular increments (e.g., 15°) through a specified angle (e.g., an angle obtained by subtracting the prescribed angular increment from 360°, i.e., 345°)
- prescribed angular increments e.g. 15°
- a specified angle e.g., an angle obtained by subtracting the prescribed angular increment from 360°, i.e., 345°
- a rotation correction angle is decided based upon the angle that affords the maximum value among the evaluation values representing facial likeliness.
- the image of interest is rotated using the rotation correction angle detected.
- the rotated image of interest is displayed in a display window.
- the image of interest is displayed in an orientation suitable for appreciation irrespective of the orientation in which the camera was held when the image was sensed.
- an image display control apparatus comprising evaluation-value calculating means for calculating an evaluation value, which represents facial likeliness of an image within a search area contained in an image of interest, using detection data for detecting a face image; evaluation-value calculation control means for executing angle conversion processing in such a manner that the detection data is rotated through a specified angle in prescribed angular increments, and controlling the evaluation-value calculating means in such a manner that evaluation-value calculation processing is executed every prescribed angular increment using the detection data that prevails after the angle conversion processing; rotation correction angle deciding means for deciding a rotation correction angle based upon an angle that affords a maximum value obtained in evaluation-value calculation processing at each prescribed angular increment; and display control means for controlling a display unit, in such a manner that the image of interest is rotated and displayed in a display window, using the rotation correction angle decided by the rotation correction angle deciding means.
- the second aspect of the present invention also provides a method suited to the above-described image display control apparatus. More specifically, the second aspect of the present invention provides an image display method comprising the steps of calculating an evaluation value, which represents facial likeliness of an image within a search area contained in an image of interest, using detection data for detecting a face image; executing angle conversion processing in such a manner that the detection data is rotated through a specified angle in prescribed angular increments, and executing evaluation-value calculation processing every prescribed angular increment using the detection data that prevails after the angle conversion processing; deciding a rotation correction angle based upon an angle that affords a maximum value obtained in evaluation-value calculation processing at each prescribed angular increment; and controlling a display unit, in such a manner that the image of interest is rotated and displayed in a display window, using the rotation correction angle decided.
- the second aspect of the present invention also provides a program for controlling the above-described image display control apparatus.
- an evaluation value representing the facial likeliness of an image within a search area contained in an image of interest is calculated using detection data for detecting a face image.
- Angle conversion processing is executed so as to rotate the detection data through a specified angle in prescribed angular increments, and evaluation-value calculation processing is executed every prescribed angular increment using the detection data that prevails after the angle conversion processing.
- a rotation correction angle is decided based upon an angle that affords a maximum value among evaluation values obtained in the evaluation-value calculation processing executed at each prescribed angular increment.
- the image of interest is rotated and displayed in a display window. Thus, the image of interest is displayed in an orientation suitable for appreciation irrespective of the orientation in which the camera was held when the image was sensed.
- an image display control apparatus comprising detection data storage means in which detection data for detecting a face image is stored, the detection data being data suited to each angle in a case where an image of interest has been rotated through a specified angle in prescribed angular increments, the data being stored in correspondence with each prescribed angular increment; evaluation-value calculating means for calculating, at every prescribed angular increment, an evaluation value, which represents facial likeliness of an image within a search area contained in the image of interest, using detection data that has been stored for each prescribed angular increment; rotation correction angle deciding means for deciding a rotation correction angle based upon an angle that affords a maximum value of the evaluation value representing facial likeliness at each angle by the evaluation-value calculating means; and display control means for controlling a display unit, in such a manner that the image of interest is rotated and displayed in a display window, using the rotation correction angle decided by the rotation correction angle deciding means.
- the third aspect of the present invention also provides a method suited to the above-described image display control apparatus. More specifically, the third aspect of the present invention provides an image display method comprising the steps of previously storing detection data for detecting a face image, the detection data being data suited to each angle in a case where an image of interest has been rotated through a specified angle in prescribed angular increments, the data being stored in correspondence with each prescribed angular increment; calculating, at every prescribed angular increment, an evaluation value, which represents facial likeliness of an image within a search area contained in the image of interest, using detection data that has been stored for each prescribed angular increment; deciding a rotation correction angle based upon an angle that affords a maximum value of the evaluation value representing facial likeliness at each angle; and controlling a display unit, in such a manner that the image of interest is rotated and displayed in a display window, using the rotation correction angle decided.
- the third aspect of the present invention also provides a program for controlling the above-described image display control apparatus.
- detection data that is the result of rotating an image of interest through a specified angle at prescribed angular increments is stored.
- An evaluation value representing the facial likeliness of an image within a search area contained in the image of interest is calculated at each prescribed angular increment using the items of detection data that have been stored.
- a rotation correction angle is decided based upon an angle that affords the maximum evaluation value.
- the image of interest is rotated and displayed in a display window using the rotation correction angle decided.
- the image of interest is displayed in an orientation suitable for appreciation irrespective of the orientation in which the camera was held when the image was sensed.
- the apparatus may further comprise resizing means for resizing the image of interest in such a manner that the image of interest after the rotation thereof will fit within the display window in a case where the image of interest is rotated and displayed in the display window.
- the rotation correction angle deciding means decide the rotation correction angle of the image of interest in such a manner that one side of the rectangle will be rendered horizontal.
- FIG. 1 illustrates manner of calculation of learning result for calculating an evaluation value of facial likeliness
- FIG. 2 illustrates an example result of learning
- FIG. 3 is a block diagram illustrating the electrical structure of a digital still camera
- FIG. 4 is a flowchart illustrating processing for rotating and displaying an image of interest
- FIG. 5 illustrates the manner in which an image of interest is searched using a search area
- FIG. 6 is a flowchart illustrating processing for calculating an evaluation value
- FIG. 7 illustrates an image rotated in a search area and result of learning
- FIG. 8 illustrates an image rotated in a search area and result of learning
- FIG. 9 is a flowchart illustrating processing for calculating a correction angle
- FIGS. 10 (A) to (C) illustrate resize processing for resizing a displayed image of interest
- FIG. 11 is a flowchart illustrating processing for calculating an evaluation value according to a second embodiment of the invention.
- FIG. 12 illustrates an image rotated in a search area and result of learning according to the second embodiment of the invention
- FIG. 13 illustrates an image rotated in a search area and result of learning according to the second embodiment of the invention.
- FIG. 14 illustrates an image rotated in a search area and result of learning.
- a digital still camera is capable of reproducing the image of a subject obtained by image sensing. More particularly, according to this embodiment, the image of a face is detected from the image of a subject (an image of interest), and the image of the subject is displayed upon being rotated based upon the sensed image of the face in such a manner that the image of a person in the image of the subject will be made upright. Even in a case where the digital still camera is held in such a manner that the image of the subject obtained by image sensing is long vertically, the image of a person will be displayed upright.
- FIG. 1 illustrates the manner in which result of learning (detection data) utilized in the detection of a face image is generated in this embodiment.
- Face image data and non-face image data is used as prelearning image data.
- Data representing images FI 1 , FI 2 , FI 3 , etc. of various faces is used for the face image data.
- Data representing non-face images, namely images that are not faces (which may be images that do or do not resemble the images of faces) FN 1 , FN 2 , FN 3 , etc., is used for the non-face image data.
- Result of learning for determining whether an image is a face image or not is obtained in accordance with a prescribed learning algorithm using these items of prelearning image data.
- Data representing result of learning is stored in a digital camera.
- FIG. 2 illustrates an example of a table representing result of learning.
- Result of learning has been stored as pixel values at prescribed positions within a search area, pixel values at prescribed positions within the search area in a case where filter processing has been applied to an image within the search area, the differences between pixel values, and the scores of these values.
- a corresponding score (which may be positive or negative) is obtained from a value such as a certain pixel value, and a value obtained by accumulating the obtained scores becomes an evaluation value indicative of the facial likeliness of an image within the search area (i.e., the degree to which the image within the search area is face-like).
- FIG. 3 is a block diagram illustrating the electrical structure of a digital still camera.
- the overall operation of the digital still camera is controlled by a control circuit 20 .
- the control circuit 20 includes a CPU 21 , a ROM 22 and a RAM 23 interconnected by a bus. Data representing result of learning as described above has been stored in the ROM 22 . It goes without saying that template image data representing the image of a face may be stored in the ROM 22 rather than result of learning having the form of a table or the like as described above.
- the RAM 23 stores image data representing the image within the search area, as well as other image data.
- the digital still camera includes an operating device 15 having a shutter-release button and a mode setting dial, etc.
- An operating signal that is output from the operating device 15 is input to the control circuit 20 .
- the zoom position of a zoom lens (the lens need not necessarily be a zoom lens) is controlled by a lens driving circuit 11 .
- the aperture of a diaphragm 2 is controlled by a diaphragm driving circuit 12 .
- a light beam representing the image of a subject is condensed by the zoom lens 1 and impinges upon an image sensing device 3 such as a CCD through the diaphragm 2 .
- a light image representing the image of the subject is formed on the photoreceptor surface of the image sensing device 3 .
- the image sensing device 3 is controlled by a control circuit 13 for the image sensing device 3 , which outputs a video signal representing the image of the subject.
- the video signal is subjected to analog signal processing such as correlated double sampling in an analog signal processing circuit 4 .
- the video signal that is output from the analog signal processing circuit 4 is converted to digital image data in analog/digital signal processing circuit 5 and the digital image data is input to the control circuit 20 and to a digital signal processing circuit 6 .
- Digital signal processing such as a gamma correction and white balance adjustment is executed in the digital signal processing circuit 6 .
- the image data that has been output from the digital signal processing circuit 6 is applied to a display control circuit 10 via a memory 7 .
- the image of the subject is displayed on the display screen of a display unit 16 by the display control circuit 10 .
- the image of the subject is sensed again and image data representing the image of the subject is obtained in a manner similar to that described above.
- the image data is applied from the digital signal processing circuit 6 to the memory 7 , where the data is stored temporarily.
- the image data is read out of the memory 7 and is recorded on a memory card 9 by a recording/readout control circuit 8 . It goes without saying data compression may applied as necessary.
- image data representing the image of the subject is read out of the memory card 9 by the recording/readout control circuit 8 .
- the image data that has been read out is input to a face detection processing circuit 14 through the memory 7 and digital signal processing circuit 6 (with data expansion processing being executed as necessary).
- Image data representing a detected face image is applied to and stored temporarily in the RAM 23 .
- Image data representing the image of the subject also is stored temporarily in the RAM 23 within the control circuit 20 .
- Display angle correction processing correctionion processing that is based upon a rotation correction angle
- This correction processing can be performed easily by an operation for addressing the image data.
- the subject image data that has undergone display angle correction processing is applied to the display control circuit 10 via the digital signal processing circuit 6 and memory 7 .
- the image of the subject in which the image of the person has been rendered upright is displayed on the display screen of the display unit 16 .
- FIG. 4 is a flowchart illustrating processing for rotating and displaying an image of interest
- FIG. 5 illustrates the relationship between an image of interest and a search area.
- This processing causes the search area to be scanned across the image of interest so that the degree of matching between the image within the search area and the above-mentioned result of learning (detection data) is evaluated. Further, as will be described later, the image within the search area is rotated in prescribed angular increments and processing for calculating an evaluation value is executed at each prescribed angle through which the image has been rotated incrementally. The image of a portion specified as by the position of the search area for which the maximum evaluation value has been obtained is judged to be the image of a face.
- the maximum value of the evaluation value is reset to zero (step 31 ). Further, a search area AS is moved to the beginning of an image of interest I (step 31 ). In this embodiment, the size of the image of interest becomes gradually smaller and the image of interest diminishes to a prescribed minimum image size. An evaluation value of facial likeliness is calculated with regard to the image within the search area AS at each size. It is determined, therefore, whether the image size of the image of interest has become the prescribed minimum image size (step 32 ).
- step 32 If the minimum image size has been attained (“YES” at step 32 ), processing for calculating the evaluation value will have been executed at various sizes and therefore the image of interest is displayed upon being rotated based upon the maximum evaluation value obtained. If the minimum image size has not been reached (“NO” at step 32 ), then it is determined whether the search area AS is at the end of the image of interest I (step 33 ).
- step 34 If the search area AS is at the end of the image of interest I (“YES” at step 33 ), evaluation value calculation processing regarding the image of interest will have ended. Processing for resizing the image of interest I is executed, therefore, in such a manner that evaluation value calculation processing will be executed with regard to an image of interest I 1 of the next smaller size (step 34 ). Further, the search area AS is moved to the beginning of the image of interest that has been resized. If the search area AS is not at the end of the image of interest (“NO” at step 33 ), then an evaluation value indicating the facial likeliness of the image within the search area AS is calculated (step 34 ). The details of processing for calculating the evaluation value will be described later. When processing for calculating the evaluation value ends, the search area is moved a small distance in the horizontal and vertical directions (step 35 ). The processing of steps 33 and 34 is repeated.
- evaluation value calculation processing is repeated until the image size reaches the minimum image size, as by applying this processing to image of interest I 1 of smaller size and to image of interest I 2 of still smaller size.
- FIG. 6 is a flowchart illustrating processing for calculating an evaluation value (the processing at step 34 in FIG. 4 ).
- the image in search area AS is rotated at increments of 15° about the center of the search area AS and an evaluation value indicating the extent to which the image is face-like is calculated using the result of learning regarding the rotated image within the search area AS.
- a rotational manipulated variable ⁇ indicating angle of rotation of the image within the search area AS is reset to zero (step 41 ).
- the rotational manipulated variable ⁇ reaches 360°, the image within the search area AS will have made one complete revolution.
- the rotational manipulated variable ⁇ becomes equal to or greater 360°, therefore (“NO” at step 42 )
- processing for calculating the evaluation value at this position of the search area AS ends.
- the manipulated variable ⁇ is less than 360° (“YES” at step 42 )
- the image within the search area AS is rotated by the rotational manipulated variable ⁇ (where counter-clockwise is taken as being the positive direction) and the evaluation value of the image within the search area AS is calculated using the result of learning (step 43 ).
- step 44 If the evaluation value obtained is larger than the maximum value (“YES” at step 44 ), then this evaluation value is adopted anew as the maximum value and the rotational manipulated variable ⁇ , the position of the search area and the size information of the image of interest are stored (step 45 ). If the evaluation value obtained is not larger than the maximum value (“NO” at step 44 ), then the processing of step 45 is skipped.
- the manipulated variable ⁇ is increased by 15° (step 46 ) and the image within the search area AS is rotated through the angle specified by the increased manipulated variable ⁇ . Processing for calculating the evaluation value is repeated in similar fashion using the result of learning regarding the rotated image within the search area AS.
- the rotational manipulated variable ⁇ is increased in increments of 15°
- the evaluation value of facial likeliness is calculated with regard to the image, which has been rotated incrementally by the manipulated variable ⁇ (i.e., through 15°, 30°, 45°, . . . ), within the search area AS, as the maximum value among these obtained evaluation values is stored.
- processing for calculating the evaluation value is executed with regard to all areas of many images of interest of different sizes and the manipulated variable ⁇ that affords the largest evaluation value is stored. For instance, in the example of FIG.
- the evaluation value of facial likeliness obtained based upon the result of learning is maximized in a case where the manipulated variable ⁇ of the image within search area AS 1 is zero with regard to an image of interest I 1 .
- FIG. 7 illustrates the image within the search area AS 1 and result R of learning for detecting facial likeliness.
- the learning result R is displayed as a template image in order to facilitate comprehension.
- An image i 11 within the search area AS 1 is one that has no inclination.
- the evaluation value of facial likeliness of the image i 11 within the search area AS 1 for which the rotational manipulated variable ⁇ is zero is calculated using the result of learning.
- the rotational manipulated variable ⁇ is increased by 15° and the evaluation value of facial likeliness of an image i 12 (where the image after the rotation thereof is indicated at i 12 , etc.) within a search area AS 2 for which the rotational manipulated variable ⁇ is 15° is calculated.
- a frame F 1 obtained by rotating the search area AS 1 through the rotational manipulated variable ⁇ of 15° is imagined in such a manner that a rotational manipulated variable ⁇ of between 15 and 345° is indicated typically by a rotational manipulated variable ⁇ of 15°.
- a frame F 12 for which the size of the frame F 2 takes on a size the same as that of the frame F 1 is determined (the frame F 12 has a size and orientation identical with those of the search area AS 1 ).
- the evaluation value of facial likeliness of the image i 12 within the frame F 12 is calculated based upon the result of learning.
- the evaluation values of facial likeliness of images within frames from F 13 to Fin obtained in similar fashion are calculated with regard to the other rotational manipulated variables ⁇ of 30 to 345°.
- the image ill has no inclination and therefore the evaluation value of facial likeliness with respect to the image ill for which the rotational manipulated variable ⁇ is zero is the maximum value. This is stored together with the position, etc., of the search area AS 1 whose rotational manipulated variable ⁇ is zero.
- the rotational manipulated variable ⁇ is zero.
- the correction angle ⁇ is zero and the image of interest is displayed without undergoing a rotational correction.
- FIG. 8 illustrates another example of the image within a search area and result of learning for detecting facial likeliness.
- an image i 21 within a search area AS 2 contained in an image of interest I is inclined leftward (in the counter-clockwise direction) by 30°.
- the correction angle ⁇ becomes zero when the image of interest I 2 is displayed, as mentioned above.
- FIG. 9 is a flowchart illustrating processing for displaying an image of interest
- FIG. 10 which shows an image of interest, illustrates the manner in which processing is executed for resizing the image of interest performed in processing for displaying the image of interest.
- the person will be closer to the upright state if the display angle is not corrected. Accordingly, the image of interest is displayed as is without the display angle being corrected (step 52 ).
- the correction angle ⁇ is set to 270° (step 54 ).
- the image of interest is rotated through an angle of 270°.
- Resize processing therefore, is applied to the image of interest (step 55 ).
- an image I of interest that is in the landscape format is being displayed in a display window (or on a display screen) w.
- the display window w has a height h 1 and a width w 1 .
- the image of interest following the rotation thereof can no longer be displayed within the display window w.
- the size of the image of interest is resized in such a manner that the width w 2 of the image of interest prevailing at the time of the landscape-type display will become the height h 1 of the window w.
- the size of the image of interest obtained by such resizing is such that height becomes h 2 and the width w 2 when the display is presented in the landscape format, as illustrated at (B) in FIG. 10 . Even if the image of interest that has been resized is displayed upon being rotated by 270°, the image of interest will fit into the display window w, as illustrated at (C) in FIG. 10 .
- the correction angle ⁇ is set to 180° (step 58 ).
- the image of interest is displayed upon being rotated by the set correction angle of 180° (step 59 ).
- the correction angle ⁇ is set to 90° (step 61 ).
- the display of the image of interest changes from the landscape to the portrait format and therefore the image of interest is subjected to resize processing in a manner similar to that of the case where the inclination of the face is equal to or greater than 45° and less than 135° (step 62 ).
- the image of interest thus resized is displayed upon being rotated through a correction angle ⁇ of 90° (step 63 ).
- the display angle of the image of interest is rotated in accordance with the inclination of the face in such a manner that the image of interest becomes easier to view.
- FIGS. 11 to 13 Another embodiment of the invention will be described with reference to FIGS. 11 to 13 .
- an image within a search area is rotated through a specified angle in prescribed angular increments and processing for calculating an evaluation value of facial likeliness is executed at each angular increment.
- an image within a search area is not rotated. Rather, the result of learning is rotated through a specified angle in prescribed angular increments (this corresponds to processing for calculating a learning result that enables detection of the image of a face that has been rotated by the prescribed angular increments) and processing for calculating an evaluation value of facial likeliness is executed at each angular increment.
- FIG. 11 is a flowchart illustrating processing (which corresponds to FIG. 6 ) for calculating an evaluation value.
- Inclination ⁇ of a learning result (since the inclination of the learning result corresponds to the above-mentioned inclination of a face, use is made of the same character ⁇ as that employed for the inclination of the face) is reset to zero (step 71 ). It is determined whether the inclination ⁇ of the learning result is less than 360°. If the inclination ⁇ is less than 360° (“YES” at step 72 ), then the learning result is rotated through the angle of the inclination ⁇ and the evaluation value of facial likeliness of the image within the search area AS is calculated using the result of learning that has been rotated (step 73 ).
- step 74 It is determined whether the evaluation value calculated is greater than the maximum evaluation value (step 74 ). If the evaluation value calculated is larger than the maximum value (“YES” at step 74 ), then the angle of rotation (inclination ⁇ ) of the learning result that has afforded this maximum value, the position in the image of interest within the search area and the size of the image of interest are stored together with this maximum value (step 75 ). The inclination ⁇ is increased by 15° (step 76 ) and processing from step 72 to step 75 is repeated.
- FIG. 12 illustrates the relationship between an image within the search area AS 1 and result of learning.
- the image i 11 of the face within the search area AS 1 is one that has no inclination.
- the evaluation value of facial likeliness of the image i 11 within the search area AS 1 is calculated using a learning result r 1 that prevails at an inclination ⁇ of zero.
- the inclination ⁇ is increased by 15° and the evaluation value of facial likeliness of the image i 11 within the search area AS is calculated using a learning result r 2 that prevails at an inclination ⁇ of 15°.
- the face image i 11 contained in the search area AS 1 has no inclination and therefore the evaluation value obtained when use is made of the learning result r 1 for which the inclination ⁇ is zero is the maximum value.
- the inclination of the learning result r 1 , etc., is stored in the manner mentioned earlier.
- the inclination ⁇ is zero.
- the correction angle ⁇ is zero and the image of interest I is displayed without undergoing a rotational correction, as mentioned above.
- FIG. 13 illustrates the relationship between the image i 21 within the search area AS 2 and result of learning.
- image i 21 within the search area AS 2 contained in the image of interest I 2 is inclined leftward (in the counter-clockwise direction) by 30°.
- the inclination for learning result r 3 is stored, as described earlier.
- the correction angle ⁇ becomes zero when the image of interest I 2 is displayed (step 52 in FIG. 9 ).
- FIG. 14 also illustrates the relationship between an image i 31 within a search area AS 3 and result of learning.
- An image of interest I 3 is one obtained by sensing an image when a digital still camera is held vertically.
- evaluation values of facial likeliness of the image within the search area AS of image of interest I 3 are calculated using learning results r 1 to rn obtained by increasing the inclination ⁇ from 0 to 345° in increments of 15°.
- the image of interest I 3 is subjected to resizing processing in a case where the image of interest I 3 will not fit within the display window owing to rotation of the image of interest I 3 by 90°.
- resize processing need not necessarily be executed.
- the result obtained by inclining the result of learning by the inclination ⁇ is calculated on each occasion.
- the calculation processing may be executed in advance and the result of learning obtained by inclination at the inclination ⁇ may be stored beforehand.
- the learning results thus stored would be stored in, e.g., ROM 22 and used in processing for calculating an evaluation value of facial likeliness in the manner described above.
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Image Processing (AREA)
- Editing Of Facsimile Originals (AREA)
- Image Analysis (AREA)
- Studio Devices (AREA)
Abstract
Description
- 1. Field of the Invention
- This invention relates to an image display control apparatus and method and to a program for controlling the image display control apparatus.
- 2. Description of the Related Art
- When the image of a subject is sensed using a digital still camera or the like, generally the camera is held so as to be suitable for a landscape-type display. However, a camera is not always held so as to be suitable for a landscape display and there are instances where a camera is held so as to be suitable for a portrait-type display. In a case where the image is displayed, however, generally the set-up is such that the image is displayed in the landscape-type format. In order to display in portrait format an image that has been captured in the portrait format, therefore, it is necessary to designate the image and rotate it in such a manner that it will be displayed in the landscape format.
- In art disclosed heretofore (Japanese Patent Application Laid-Open No. 8-138024), the above-mentioned facts are taken into consideration and in a case where the subject is a person, the orientation of an image is discriminated based upon the positional relationship of the constituent parts of the body of the person.
- However, with regard to an image that does not contain the constituent part of a body other than a face, as in the case of portrait photography, there are instances where image orientation cannot be determined.
- Accordingly, an object of the present invention is to discriminate the orientation of an image and rotate the image upon rotating it in a direction suitable for the display.
- According to a first aspect of the present invention, the foregoing object is attained by providing an image display control apparatus comprising in-area-image rotating means for rotating an image, which is located within a search area contained in an image of interest, through a specified angle in prescribed angular increments; evaluation-value calculating means for calculating an evaluation value, which represents facial likeliness of an image within the search area at each angle through which the image has been rotated in the prescribed angular increments by the in-area-image rotating means, using detection data for detecting a face image; rotation correction angle deciding means for deciding a rotation correction angle based upon an angle that affords a maximum value of the evaluation value representing facial likeliness at each angle by the evaluation-value calculating means; and display control means for controlling a display unit, in such a manner that the image of interest is rotated and displayed in a display window, using the rotation correction angle decided by the rotation correction angle deciding means.
- The first aspect of the present invention also provides a method suited to the above-described image display control apparatus. More specifically, the first aspect of the present invention provides an image display method comprising the steps of rotating an image, which is located within a search area contained in an image of interest, through a specified angle in prescribed angular increments; calculating an evaluation value, which represents facial likeliness of an image within the search area at each angle through which the image has been rotated in the prescribed angular increments, using detection data for detecting a face image; deciding a rotation correction angle based upon an angle that affords a maximum value of the evaluation value representing facial likeliness at each angle; and controlling a display unit, in such a manner that the image of interest is rotated and displayed in a display window, using the rotation correction angle decided.
- The first aspect of the present invention also provides a program for controlling the above-described image display control apparatus.
- In accordance with the first aspect of the present invention, an image within a search area that is included in an image of interest to be displayed (the size of the search area may be smaller than or the same as the size of the image of interest) is rotated in prescribed angular increments (e.g., 15°) through a specified angle (e.g., an angle obtained by subtracting the prescribed angular increment from 360°, i.e., 345°) By using detection data that is for detecting a face image, an evaluation value representing the facial likeliness of an image within the search area (i.e., the degree to which the image within the search area is face-like) is calculated with regard to the image within the search area that has been rotated through the prescribed angular increment. A rotation correction angle is decided based upon the angle that affords the maximum value among the evaluation values representing facial likeliness. The image of interest is rotated using the rotation correction angle detected. The rotated image of interest is displayed in a display window. Thus, the image of interest is displayed in an orientation suitable for appreciation irrespective of the orientation in which the camera was held when the image was sensed.
- According to a second aspect of the present invention, the foregoing object is attained by providing an image display control apparatus comprising evaluation-value calculating means for calculating an evaluation value, which represents facial likeliness of an image within a search area contained in an image of interest, using detection data for detecting a face image; evaluation-value calculation control means for executing angle conversion processing in such a manner that the detection data is rotated through a specified angle in prescribed angular increments, and controlling the evaluation-value calculating means in such a manner that evaluation-value calculation processing is executed every prescribed angular increment using the detection data that prevails after the angle conversion processing; rotation correction angle deciding means for deciding a rotation correction angle based upon an angle that affords a maximum value obtained in evaluation-value calculation processing at each prescribed angular increment; and display control means for controlling a display unit, in such a manner that the image of interest is rotated and displayed in a display window, using the rotation correction angle decided by the rotation correction angle deciding means.
- The second aspect of the present invention also provides a method suited to the above-described image display control apparatus. More specifically, the second aspect of the present invention provides an image display method comprising the steps of calculating an evaluation value, which represents facial likeliness of an image within a search area contained in an image of interest, using detection data for detecting a face image; executing angle conversion processing in such a manner that the detection data is rotated through a specified angle in prescribed angular increments, and executing evaluation-value calculation processing every prescribed angular increment using the detection data that prevails after the angle conversion processing; deciding a rotation correction angle based upon an angle that affords a maximum value obtained in evaluation-value calculation processing at each prescribed angular increment; and controlling a display unit, in such a manner that the image of interest is rotated and displayed in a display window, using the rotation correction angle decided.
- The second aspect of the present invention also provides a program for controlling the above-described image display control apparatus.
- In accordance with the second aspect of the present invention, an evaluation value representing the facial likeliness of an image within a search area contained in an image of interest is calculated using detection data for detecting a face image. Angle conversion processing is executed so as to rotate the detection data through a specified angle in prescribed angular increments, and evaluation-value calculation processing is executed every prescribed angular increment using the detection data that prevails after the angle conversion processing. A rotation correction angle is decided based upon an angle that affords a maximum value among evaluation values obtained in the evaluation-value calculation processing executed at each prescribed angular increment. The image of interest is rotated and displayed in a display window. Thus, the image of interest is displayed in an orientation suitable for appreciation irrespective of the orientation in which the camera was held when the image was sensed.
- According to a third aspect of the present invention, the foregoing object is attained by providing an image display control apparatus comprising detection data storage means in which detection data for detecting a face image is stored, the detection data being data suited to each angle in a case where an image of interest has been rotated through a specified angle in prescribed angular increments, the data being stored in correspondence with each prescribed angular increment; evaluation-value calculating means for calculating, at every prescribed angular increment, an evaluation value, which represents facial likeliness of an image within a search area contained in the image of interest, using detection data that has been stored for each prescribed angular increment; rotation correction angle deciding means for deciding a rotation correction angle based upon an angle that affords a maximum value of the evaluation value representing facial likeliness at each angle by the evaluation-value calculating means; and display control means for controlling a display unit, in such a manner that the image of interest is rotated and displayed in a display window, using the rotation correction angle decided by the rotation correction angle deciding means.
- The third aspect of the present invention also provides a method suited to the above-described image display control apparatus. More specifically, the third aspect of the present invention provides an image display method comprising the steps of previously storing detection data for detecting a face image, the detection data being data suited to each angle in a case where an image of interest has been rotated through a specified angle in prescribed angular increments, the data being stored in correspondence with each prescribed angular increment; calculating, at every prescribed angular increment, an evaluation value, which represents facial likeliness of an image within a search area contained in the image of interest, using detection data that has been stored for each prescribed angular increment; deciding a rotation correction angle based upon an angle that affords a maximum value of the evaluation value representing facial likeliness at each angle; and controlling a display unit, in such a manner that the image of interest is rotated and displayed in a display window, using the rotation correction angle decided.
- The third aspect of the present invention also provides a program for controlling the above-described image display control apparatus.
- In accordance with the third aspect of the present invention, detection data that is the result of rotating an image of interest through a specified angle at prescribed angular increments is stored. An evaluation value representing the facial likeliness of an image within a search area contained in the image of interest is calculated at each prescribed angular increment using the items of detection data that have been stored. A rotation correction angle is decided based upon an angle that affords the maximum evaluation value. The image of interest is rotated and displayed in a display window using the rotation correction angle decided. Thus, the image of interest is displayed in an orientation suitable for appreciation irrespective of the orientation in which the camera was held when the image was sensed.
- The apparatus may further comprise resizing means for resizing the image of interest in such a manner that the image of interest after the rotation thereof will fit within the display window in a case where the image of interest is rotated and displayed in the display window.
- Further, in a case where the display window is a rectangle, it is preferred that the rotation correction angle deciding means decide the rotation correction angle of the image of interest in such a manner that one side of the rectangle will be rendered horizontal.
- Other features and advantages of the present invention will be apparent from the following description taken in conjunction with the accompanying drawings, in which like reference characters designate the same or similar parts throughout the figures thereof.
-
FIG. 1 illustrates manner of calculation of learning result for calculating an evaluation value of facial likeliness; -
FIG. 2 illustrates an example result of learning; -
FIG. 3 is a block diagram illustrating the electrical structure of a digital still camera; -
FIG. 4 is a flowchart illustrating processing for rotating and displaying an image of interest; -
FIG. 5 illustrates the manner in which an image of interest is searched using a search area; -
FIG. 6 is a flowchart illustrating processing for calculating an evaluation value; -
FIG. 7 illustrates an image rotated in a search area and result of learning; -
FIG. 8 illustrates an image rotated in a search area and result of learning; -
FIG. 9 is a flowchart illustrating processing for calculating a correction angle; - FIGS. 10(A) to (C) illustrate resize processing for resizing a displayed image of interest;
-
FIG. 11 is a flowchart illustrating processing for calculating an evaluation value according to a second embodiment of the invention; -
FIG. 12 illustrates an image rotated in a search area and result of learning according to the second embodiment of the invention; -
FIG. 13 illustrates an image rotated in a search area and result of learning according to the second embodiment of the invention; and -
FIG. 14 illustrates an image rotated in a search area and result of learning. - A preferred embodiment of the present invention will now be described in detail with reference to the drawings.
- A digital still camera according to this embodiment is capable of reproducing the image of a subject obtained by image sensing. More particularly, according to this embodiment, the image of a face is detected from the image of a subject (an image of interest), and the image of the subject is displayed upon being rotated based upon the sensed image of the face in such a manner that the image of a person in the image of the subject will be made upright. Even in a case where the digital still camera is held in such a manner that the image of the subject obtained by image sensing is long vertically, the image of a person will be displayed upright.
-
FIG. 1 illustrates the manner in which result of learning (detection data) utilized in the detection of a face image is generated in this embodiment. - Face image data and non-face image data is used as prelearning image data. Data representing images FI1, FI2, FI3, etc. of various faces is used for the face image data. Data representing non-face images, namely images that are not faces (which may be images that do or do not resemble the images of faces) FN1, FN2, FN3, etc., is used for the non-face image data.
- Result of learning for determining whether an image is a face image or not is obtained in accordance with a prescribed learning algorithm using these items of prelearning image data. Data representing result of learning is stored in a digital camera.
-
FIG. 2 illustrates an example of a table representing result of learning. - Result of learning has been stored as pixel values at prescribed positions within a search area, pixel values at prescribed positions within the search area in a case where filter processing has been applied to an image within the search area, the differences between pixel values, and the scores of these values. A corresponding score (which may be positive or negative) is obtained from a value such as a certain pixel value, and a value obtained by accumulating the obtained scores becomes an evaluation value indicative of the facial likeliness of an image within the search area (i.e., the degree to which the image within the search area is face-like).
-
FIG. 3 is a block diagram illustrating the electrical structure of a digital still camera. - Processing executed when an image is sensed will be described before reproduction is described.
- The overall operation of the digital still camera is controlled by a
control circuit 20. - The
control circuit 20 includes aCPU 21, aROM 22 and aRAM 23 interconnected by a bus. Data representing result of learning as described above has been stored in theROM 22. It goes without saying that template image data representing the image of a face may be stored in theROM 22 rather than result of learning having the form of a table or the like as described above. TheRAM 23 stores image data representing the image within the search area, as well as other image data. - The digital still camera includes an operating
device 15 having a shutter-release button and a mode setting dial, etc. An operating signal that is output from the operatingdevice 15 is input to thecontrol circuit 20. - The zoom position of a zoom lens (the lens need not necessarily be a zoom lens) is controlled by a
lens driving circuit 11. The aperture of adiaphragm 2 is controlled by adiaphragm driving circuit 12. A light beam representing the image of a subject is condensed by thezoom lens 1 and impinges upon animage sensing device 3 such as a CCD through thediaphragm 2. A light image representing the image of the subject is formed on the photoreceptor surface of theimage sensing device 3. - If an image sensing mode is set by a mode setting dial, the
image sensing device 3 is controlled by acontrol circuit 13 for theimage sensing device 3, which outputs a video signal representing the image of the subject. The video signal is subjected to analog signal processing such as correlated double sampling in an analogsignal processing circuit 4. The video signal that is output from the analogsignal processing circuit 4 is converted to digital image data in analog/digitalsignal processing circuit 5 and the digital image data is input to thecontrol circuit 20 and to a digitalsignal processing circuit 6. Digital signal processing such as a gamma correction and white balance adjustment is executed in the digitalsignal processing circuit 6. - The image data that has been output from the digital
signal processing circuit 6 is applied to adisplay control circuit 10 via amemory 7. The image of the subject is displayed on the display screen of adisplay unit 16 by thedisplay control circuit 10. - If the shutter-release button is pressed, the image of the subject is sensed again and image data representing the image of the subject is obtained in a manner similar to that described above. The image data is applied from the digital
signal processing circuit 6 to thememory 7, where the data is stored temporarily. The image data is read out of thememory 7 and is recorded on amemory card 9 by a recording/readout control circuit 8. It goes without saying data compression may applied as necessary. - If a playback mode is set by the mode setting dial, image data representing the image of the subject is read out of the
memory card 9 by the recording/readout control circuit 8. The image data that has been read out is input to a facedetection processing circuit 14 through thememory 7 and digital signal processing circuit 6 (with data expansion processing being executed as necessary). Image data representing a detected face image is applied to and stored temporarily in theRAM 23. Image data representing the image of the subject also is stored temporarily in theRAM 23 within thecontrol circuit 20. Display angle correction processing (correction processing that is based upon a rotation correction angle) of the image data representing the image of the subject is executed in such a manner that the face image will be rendered upright. This correction processing can be performed easily by an operation for addressing the image data. - The subject image data that has undergone display angle correction processing is applied to the
display control circuit 10 via the digitalsignal processing circuit 6 andmemory 7. Thus, the image of the subject in which the image of the person has been rendered upright is displayed on the display screen of thedisplay unit 16. -
FIG. 4 is a flowchart illustrating processing for rotating and displaying an image of interest, andFIG. 5 illustrates the relationship between an image of interest and a search area. - This processing causes the search area to be scanned across the image of interest so that the degree of matching between the image within the search area and the above-mentioned result of learning (detection data) is evaluated. Further, as will be described later, the image within the search area is rotated in prescribed angular increments and processing for calculating an evaluation value is executed at each prescribed angle through which the image has been rotated incrementally. The image of a portion specified as by the position of the search area for which the maximum evaluation value has been obtained is judged to be the image of a face.
- First, the maximum value of the evaluation value is reset to zero (step 31). Further, a search area AS is moved to the beginning of an image of interest I (step 31). In this embodiment, the size of the image of interest becomes gradually smaller and the image of interest diminishes to a prescribed minimum image size. An evaluation value of facial likeliness is calculated with regard to the image within the search area AS at each size. It is determined, therefore, whether the image size of the image of interest has become the prescribed minimum image size (step 32).
- If the minimum image size has been attained (“YES” at step 32), processing for calculating the evaluation value will have been executed at various sizes and therefore the image of interest is displayed upon being rotated based upon the maximum evaluation value obtained. If the minimum image size has not been reached (“NO” at step 32), then it is determined whether the search area AS is at the end of the image of interest I (step 33).
- If the search area AS is at the end of the image of interest I (“YES” at step 33), evaluation value calculation processing regarding the image of interest will have ended. Processing for resizing the image of interest I is executed, therefore, in such a manner that evaluation value calculation processing will be executed with regard to an image of interest I1 of the next smaller size (step 34). Further, the search area AS is moved to the beginning of the image of interest that has been resized. If the search area AS is not at the end of the image of interest (“NO” at step 33), then an evaluation value indicating the facial likeliness of the image within the search area AS is calculated (step 34). The details of processing for calculating the evaluation value will be described later. When processing for calculating the evaluation value ends, the search area is moved a small distance in the horizontal and vertical directions (step 35). The processing of
steps - Thus, when processing for calculating an evaluation value of facial likeliness regarding the image within the search area AS ends with regard to the initial image of interest, evaluation value calculation processing is repeated until the image size reaches the minimum image size, as by applying this processing to image of interest I1 of smaller size and to image of interest I2 of still smaller size.
-
FIG. 6 is a flowchart illustrating processing for calculating an evaluation value (the processing atstep 34 inFIG. 4 ). - In this processing, the image in search area AS is rotated at increments of 15° about the center of the search area AS and an evaluation value indicating the extent to which the image is face-like is calculated using the result of learning regarding the rotated image within the search area AS.
- First, a rotational manipulated variable θ indicating angle of rotation of the image within the search area AS is reset to zero (step 41). When the rotational manipulated variable θ reaches 360°, the image within the search area AS will have made one complete revolution. When the rotational manipulated variable θ becomes equal to or greater 360°, therefore (“NO” at step 42), then processing for calculating the evaluation value at this position of the search area AS ends. If the manipulated variable θ is less than 360° (“YES” at step 42), then the image within the search area AS is rotated by the rotational manipulated variable θ (where counter-clockwise is taken as being the positive direction) and the evaluation value of the image within the search area AS is calculated using the result of learning (step 43).
- If the evaluation value obtained is larger than the maximum value (“YES” at step 44), then this evaluation value is adopted anew as the maximum value and the rotational manipulated variable θ, the position of the search area and the size information of the image of interest are stored (step 45). If the evaluation value obtained is not larger than the maximum value (“NO” at step 44), then the processing of
step 45 is skipped. The manipulated variable θ is increased by 15° (step 46) and the image within the search area AS is rotated through the angle specified by the increased manipulated variable θ. Processing for calculating the evaluation value is repeated in similar fashion using the result of learning regarding the rotated image within the search area AS. - Thus, the rotational manipulated variable θ is increased in increments of 15°, the evaluation value of facial likeliness is calculated with regard to the image, which has been rotated incrementally by the manipulated variable θ (i.e., through 15°, 30°, 45°, . . . ), within the search area AS, as the maximum value among these obtained evaluation values is stored. As mentioned above, processing for calculating the evaluation value is executed with regard to all areas of many images of interest of different sizes and the manipulated variable θ that affords the largest evaluation value is stored. For instance, in the example of
FIG. 7 , the evaluation value of facial likeliness obtained based upon the result of learning is maximized in a case where the manipulated variable θ of the image within search area AS1 is zero with regard to an image of interest I1. Inclination α (=360°−θ) of the face within the image of interest I1 is zero at this time. -
FIG. 7 illustrates the image within the search area AS1 and result R of learning for detecting facial likeliness. The learning result R is displayed as a template image in order to facilitate comprehension. - An image i11 within the search area AS1 is one that has no inclination.
- The evaluation value of facial likeliness of the image i11 within the search area AS1 for which the rotational manipulated variable θ is zero is calculated using the result of learning. Next, the rotational manipulated variable θ is increased by 15° and the evaluation value of facial likeliness of an image i12 (where the image after the rotation thereof is indicated at i12, etc.) within a search area AS2 for which the rotational manipulated variable θ is 15° is calculated. Similarly calculated are evaluation values of facial likeliness of images i13, i14 for which the rotational manipulated variables θ are 30° and 45°, respectively, after having been increased by a further 15° and then by a further 15°. This is continued up to evaluation value calculation processing with respect to an image i1 n for which the manipulated variable θ is 345°, and the maximum evaluation value is obtained in the manner described above.
- A frame F1 obtained by rotating the search area AS1 through the rotational manipulated variable θ of 15° is imagined in such a manner that a rotational manipulated variable θ of between 15 and 345° is indicated typically by a rotational manipulated variable θ of 15°. Consider a frame F2 in which the frame F1 is inscribed and for which the rotational manipulated variable θ is 0°. A frame F12 for which the size of the frame F2 takes on a size the same as that of the frame F1 is determined (the frame F12 has a size and orientation identical with those of the search area AS1). The evaluation value of facial likeliness of the image i12 within the frame F12 is calculated based upon the result of learning. The evaluation values of facial likeliness of images within frames from F13 to Fin obtained in similar fashion are calculated with regard to the other rotational manipulated variables θ of 30 to 345°.
- In the example illustrated in
FIG. 7 , the image ill has no inclination and therefore the evaluation value of facial likeliness with respect to the image ill for which the rotational manipulated variable θ is zero is the maximum value. This is stored together with the position, etc., of the search area AS1 whose rotational manipulated variable θ is zero. - The rotational manipulated variable θ is zero. When the image of interest I1 is displayed, therefore, the correction angle β is zero and the image of interest is displayed without undergoing a rotational correction.
-
FIG. 8 illustrates another example of the image within a search area and result of learning for detecting facial likeliness. - Here an image i21 within a search area AS2 contained in an image of interest I is inclined leftward (in the counter-clockwise direction) by 30°.
- In a manner similar to that described above, use is made of result of learning to calculate facial likeliness with regard to images i21 to i2 n obtained in a case where the rotational manipulated variable θ of the image i21 within the search area AS2 has been rotated from 0 to 345° in increments of 15°. The image i21 has a leftward inclination of 30°. In a case where the result of learning is used, therefore, the evaluation value of facial likeliness with respect to an image i2(n−1) that prevails when the rotational manipulated variable θ is 330° takes on the maximum value. The manipulated variable θ of 330° is stored together with the position of the search area AS2.
- Since the manipulated variable θ is 330°, the correction angle β becomes zero when the image of interest I2 is displayed, as mentioned above.
-
FIG. 9 is a flowchart illustrating processing for displaying an image of interest, andFIG. 10 , which shows an image of interest, illustrates the manner in which processing is executed for resizing the image of interest performed in processing for displaying the image of interest. - In processing for displaying the image of interest, use is made of the inclination of the face of the image within the search area AS that affords the maximum evaluation value. The inclination of the face is represented by α=360°−θ using the above-described rotational manipulated variable θ.
- In a case where the inclination α of the face is equal to or greater than 0° and less than 45° or equal to or greater than 315° and less than 360° (“YES” at step 51), the person will be closer to the upright state if the display angle is not corrected. Accordingly, the image of interest is displayed as is without the display angle being corrected (step 52).
- If the inclination α of the face is equal to or greater than 45° and less than 135° (“YES” at step 53), then the correction angle β is set to 270° (step 54). Thus the image of interest is rotated through an angle of 270°. By rotating the image of interest, an image of interest that is in the landscape-type format is displayed in the portrait-type format. Resize processing, therefore, is applied to the image of interest (step 55).
- With reference to (A) in
FIG. 10 , an image I of interest that is in the landscape format is being displayed in a display window (or on a display screen) w. The display window w has a height h1 and a width w1. When such an image I of interest has been rotated 270° in the counter-clockwise direction, the image of interest following the rotation thereof can no longer be displayed within the display window w. For this reason, the size of the image of interest is resized in such a manner that the width w2 of the image of interest prevailing at the time of the landscape-type display will become the height h1 of the window w. The size of the image of interest obtained by such resizing is such that height becomes h2 and the width w2 when the display is presented in the landscape format, as illustrated at (B) inFIG. 10 . Even if the image of interest that has been resized is displayed upon being rotated by 270°, the image of interest will fit into the display window w, as illustrated at (C) inFIG. 10 . - With reference again to
FIG. 9 , if the inclination α of the face is equal to or greater than 135° and less than 225° (“YES” at step 57), then the correction angle β is set to 180° (step 58). The image of interest is displayed upon being rotated by the set correction angle of 180° (step 59). - If the inclination α of the face is equal to or greater than 225° and less than 315° (“YES” at step 60), then the correction angle β is set to 90° (step 61). In this case, the display of the image of interest changes from the landscape to the portrait format and therefore the image of interest is subjected to resize processing in a manner similar to that of the case where the inclination of the face is equal to or greater than 45° and less than 135° (step 62). The image of interest thus resized is displayed upon being rotated through a correction angle β of 90° (step 63).
- Thus, the display angle of the image of interest is rotated in accordance with the inclination of the face in such a manner that the image of interest becomes easier to view.
- Another embodiment of the invention will be described with reference to FIGS. 11 to 13.
- In the embodiment described above, an image within a search area is rotated through a specified angle in prescribed angular increments and processing for calculating an evaluation value of facial likeliness is executed at each angular increment. In the embodiment illustrated next, however, an image within a search area is not rotated. Rather, the result of learning is rotated through a specified angle in prescribed angular increments (this corresponds to processing for calculating a learning result that enables detection of the image of a face that has been rotated by the prescribed angular increments) and processing for calculating an evaluation value of facial likeliness is executed at each angular increment.
-
FIG. 11 is a flowchart illustrating processing (which corresponds toFIG. 6 ) for calculating an evaluation value. - Inclination α of a learning result (since the inclination of the learning result corresponds to the above-mentioned inclination of a face, use is made of the same character α as that employed for the inclination of the face) is reset to zero (step 71). It is determined whether the inclination α of the learning result is less than 360°. If the inclination α is less than 360° (“YES” at step 72), then the learning result is rotated through the angle of the inclination α and the evaluation value of facial likeliness of the image within the search area AS is calculated using the result of learning that has been rotated (step 73).
- It is determined whether the evaluation value calculated is greater than the maximum evaluation value (step 74). If the evaluation value calculated is larger than the maximum value (“YES” at step 74), then the angle of rotation (inclination α) of the learning result that has afforded this maximum value, the position in the image of interest within the search area and the size of the image of interest are stored together with this maximum value (step 75). The inclination α is increased by 15° (step 76) and processing from
step 72 to step 75 is repeated. -
FIG. 12 illustrates the relationship between an image within the search area AS1 and result of learning. - The image i11 of the face within the search area AS1 is one that has no inclination.
- The evaluation value of facial likeliness of the image i11 within the search area AS1 is calculated using a learning result r1 that prevails at an inclination α of zero. Next, the inclination α is increased by 15° and the evaluation value of facial likeliness of the image i11 within the search area AS is calculated using a learning result r2 that prevails at an inclination α of 15°. Similarly, evaluation values of facial likeliness of the image i11 within the search area AS are calculated using learning results r3, r4 for which the inclinations α are 30° and 45°, respectively, after having been increased by a further 15°and then by a further 15°. This is continued up to evaluation value calculation processing that uses the learning result prevailing at inclination α=345°.
- In the example illustrated in
FIG. 12 , the face image i11 contained in the search area AS1 has no inclination and therefore the evaluation value obtained when use is made of the learning result r1 for which the inclination α is zero is the maximum value. The inclination of the learning result r1, etc., is stored in the manner mentioned earlier. - The inclination α is zero. When the image of interest I1 is displayed, therefore, the correction angle β is zero and the image of interest I is displayed without undergoing a rotational correction, as mentioned above.
-
FIG. 13 illustrates the relationship between the image i21 within the search area AS2 and result of learning. - Here the image i21 within the search area AS2 contained in the image of interest I2 is inclined leftward (in the counter-clockwise direction) by 30°.
- In a manner similar to that described above, the evaluation value of facial likeliness of image i21 within the search area AS2 is calculated using learning result r1 at inclination α=0°, learning result r2 at inclination α=15°, etc. Since the image i21 of the face within the search area AS2 has an inclination of 30°, the evaluation value of facial likeliness that employs learning result r3 at inclination α=30° is the maximum value. The inclination for learning result r3 is stored, as described earlier.
- Since the inclination α is 30°, the correction angle β becomes zero when the image of interest I2 is displayed (
step 52 inFIG. 9 ). - Thus, since the angle of display is not corrected when the neck of the person is somewhat inclined, it is possible to prevent a situation in which the image of interest is rendered unattractive by a correction.
-
FIG. 14 also illustrates the relationship between an image i31 within a search area AS3 and result of learning. - An image of interest I3 is one obtained by sensing an image when a digital still camera is held vertically.
- In a manner similar to that described above, evaluation values of facial likeliness of the image within the search area AS of image of interest I3 are calculated using learning results r1 to rn obtained by increasing the inclination α from 0 to 345° in increments of 15°.
- Since the image of interest I3 is one obtained by sensing an image when a digital still camera is held vertically, the evaluation value of facial likeliness that employs learning result r8 at inclination α=90° is the maximum value. Accordingly, the correction angle of image of interest I3 is 270° (
step 54 inFIG. 9 ) and the image of interest I3 is displayed upon being rotated by 270°. Thus, the image of interest I3 is displayed in an orientation suitable for appreciation. - It goes without saying that the image of interest I3 is subjected to resizing processing in a case where the image of interest I3 will not fit within the display window owing to rotation of the image of interest I3 by 90°. Of course, resize processing need not necessarily be executed.
- In the embodiment described above, the result obtained by inclining the result of learning by the inclination α is calculated on each occasion. However, the calculation processing may be executed in advance and the result of learning obtained by inclination at the inclination α may be stored beforehand. The learning results thus stored would be stored in, e.g.,
ROM 22 and used in processing for calculating an evaluation value of facial likeliness in the manner described above. - As many apparently widely different embodiments of the present invention can be made without departing from the spirit and scope thereof, it is to be understood that the invention is not limited to the specific embodiments thereof except as defined in the appended claims.
Claims (15)
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2004101784A JP4177779B2 (en) | 2004-03-31 | 2004-03-31 | Image display control device and method, and program for controlling image display control device |
JP2004-101784 | 2004-03-31 |
Publications (2)
Publication Number | Publication Date |
---|---|
US20050234324A1 true US20050234324A1 (en) | 2005-10-20 |
US9230184B2 US9230184B2 (en) | 2016-01-05 |
Family
ID=35049937
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US11/089,225 Expired - Fee Related US9230184B2 (en) | 2004-03-31 | 2005-03-25 | Image display control apparatus and method, and program for controlling image display control apparatus |
Country Status (3)
Country | Link |
---|---|
US (1) | US9230184B2 (en) |
JP (1) | JP4177779B2 (en) |
CN (1) | CN100365657C (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20080025558A1 (en) * | 2006-07-25 | 2008-01-31 | Fujifilm Corporation | Image trimming apparatus |
US20080240563A1 (en) * | 2007-03-30 | 2008-10-02 | Casio Computer Co., Ltd. | Image pickup apparatus equipped with face-recognition function |
US20090180004A1 (en) * | 2008-01-10 | 2009-07-16 | Nikon Corporation | Information displaying apparatus |
US20120252410A1 (en) * | 2011-03-28 | 2012-10-04 | Htc Corporation | Systems and Methods for Gesture Lock Obfuscation |
KR20140002540A (en) * | 2012-06-29 | 2014-01-08 | 지이 메디컬 시스템즈 글로발 테크놀러지 캄파니 엘엘씨 | Detection apparatus, apparatus for medical use, and program |
US8971613B2 (en) | 2010-07-07 | 2015-03-03 | Nec Corporation | Image processing learning device, image processing learning method, and image processing learning program |
US20180018946A1 (en) * | 2016-07-12 | 2018-01-18 | Qualcomm Incorporated | Multiple orientation detection |
US10891019B2 (en) * | 2016-02-29 | 2021-01-12 | Huawei Technologies Co., Ltd. | Dynamic thumbnail selection for search results |
Families Citing this family (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2009032022A (en) * | 2007-07-26 | 2009-02-12 | Seiko Epson Corp | Image processor, image processing method and computer program |
JP4539729B2 (en) * | 2008-02-15 | 2010-09-08 | ソニー株式会社 | Image processing apparatus, camera apparatus, image processing method, and program |
CN101465116B (en) * | 2009-01-07 | 2013-12-11 | 北京中星微电子有限公司 | Display equipment and control method thereof |
JP5226570B2 (en) * | 2009-03-19 | 2013-07-03 | グローリー株式会社 | Image detection apparatus, image detection method, and image detection program |
CN101639933B (en) * | 2009-07-16 | 2013-03-27 | 上海合合信息科技发展有限公司 | Image rotation correction method and system and electronic device |
JP5397081B2 (en) * | 2009-08-12 | 2014-01-22 | 富士通モバイルコミュニケーションズ株式会社 | Mobile device |
CN104732225B (en) * | 2013-12-24 | 2018-12-18 | 中国科学院深圳先进技术研究院 | image rotation processing method |
CN103714327B (en) * | 2013-12-30 | 2017-02-01 | 上海合合信息科技发展有限公司 | Method and system for correcting image direction |
CN104836978B (en) * | 2014-03-10 | 2019-01-22 | 腾讯科技(北京)有限公司 | The method and device of video processing |
US9942464B2 (en) * | 2014-05-27 | 2018-04-10 | Thomson Licensing | Methods and systems for media capture and seamless display of sequential images using a touch sensitive device |
JP6032252B2 (en) * | 2014-09-09 | 2016-11-24 | カシオ計算機株式会社 | Image correction apparatus, image correction method, and program |
KR101733288B1 (en) * | 2015-06-16 | 2017-05-08 | 중앙대학교 산학협력단 | Object Detecter Generation Method Using Direction Information, Object Detection Method and Apparatus using the same |
Citations (21)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5680481A (en) * | 1992-05-26 | 1997-10-21 | Ricoh Corporation | Facial feature extraction method and apparatus for a neural network acoustic and visual speech recognition system |
US5774591A (en) * | 1995-12-15 | 1998-06-30 | Xerox Corporation | Apparatus and method for recognizing facial expressions and facial gestures in a sequence of images |
US5802220A (en) * | 1995-12-15 | 1998-09-01 | Xerox Corporation | Apparatus and method for tracking facial motion through a sequence of images |
US5835616A (en) * | 1994-02-18 | 1998-11-10 | University Of Central Florida | Face detection using templates |
US5859921A (en) * | 1995-05-10 | 1999-01-12 | Mitsubishi Denki Kabushiki Kaisha | Apparatus for processing an image of a face |
US5878156A (en) * | 1995-07-28 | 1999-03-02 | Mitsubishi Denki Kabushiki Kaisha | Detection of the open/closed state of eyes based on analysis of relation between eye and eyebrow images in input face images |
US5973664A (en) * | 1998-03-19 | 1999-10-26 | Portrait Displays, Inc. | Parameterized image orientation for computer displays |
US5982912A (en) * | 1996-03-18 | 1999-11-09 | Kabushiki Kaisha Toshiba | Person identification apparatus and method using concentric templates and feature point candidates |
US6246779B1 (en) * | 1997-12-12 | 2001-06-12 | Kabushiki Kaisha Toshiba | Gaze position detection apparatus and method |
US20020150280A1 (en) * | 2000-12-04 | 2002-10-17 | Pingshan Li | Face detection under varying rotation |
US6571002B1 (en) * | 1999-05-13 | 2003-05-27 | Mitsubishi Denki Kabushiki Kaisha | Eye open/close detection through correlation |
US20030108225A1 (en) * | 2001-12-12 | 2003-06-12 | Sony Corporation | System and method for effectively extracting facial feature information |
US20030190060A1 (en) * | 2002-04-09 | 2003-10-09 | Industrial Technology Research Institute | Method for locating face landmarks in an image |
US6671391B1 (en) * | 2000-05-26 | 2003-12-30 | Microsoft Corp. | Pose-adaptive face detection system and process |
US20050100195A1 (en) * | 2003-09-09 | 2005-05-12 | Fuji Photo Film Co., Ltd. | Apparatus, method, and program for discriminating subjects |
US6950535B2 (en) * | 2000-01-31 | 2005-09-27 | Mitsubishi Denki Kabushiki Kaisha | Image collecting device, image retrieving device, and image collecting and retrieving system |
US20060078176A1 (en) * | 2004-10-08 | 2006-04-13 | Fujitsu Limited | Biometric information input device, biometric authentication device, biometric information processing method, and computer-readable recording medium recording biometric information processing program |
US20060222264A1 (en) * | 2005-03-31 | 2006-10-05 | Siemens Ag | Method for vertically orienting a face shown in a picture |
US7120279B2 (en) * | 2003-01-30 | 2006-10-10 | Eastman Kodak Company | Method for face orientation determination in digital color images |
US7158177B2 (en) * | 2002-04-04 | 2007-01-02 | Mitsubishi Electric Corporation | Apparatus for and method of synthesizing face image |
US7349558B2 (en) * | 2003-02-19 | 2008-03-25 | Konica Minolta Holdings, Inc. | Image processing method, image processing apparatus, storage medium and program |
Family Cites Families (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH08138024A (en) | 1994-11-04 | 1996-05-31 | Konica Corp | Picture direction discriminating method |
JPH08339437A (en) | 1995-06-13 | 1996-12-24 | Sony Corp | Image editing device |
JP3355068B2 (en) | 1995-07-14 | 2002-12-09 | 三菱電機株式会社 | Face image processing device |
JPH09171560A (en) | 1995-12-20 | 1997-06-30 | Oki Electric Ind Co Ltd | Device for detecting face inclination |
US6295088B1 (en) * | 1997-02-17 | 2001-09-25 | Nikon Corporation | Portable display device |
JP3848101B2 (en) * | 2001-05-17 | 2006-11-22 | シャープ株式会社 | Image processing apparatus, image processing method, and image processing program |
GB0208654D0 (en) * | 2002-04-16 | 2002-05-29 | Koninkl Philips Electronics Nv | Image processing for video or photographic equipment |
JP3913604B2 (en) | 2002-04-26 | 2007-05-09 | 富士フイルム株式会社 | How to create ID photo |
JP3781016B2 (en) * | 2002-06-18 | 2006-05-31 | カシオ計算機株式会社 | Electronic camera, photographing direction acquisition method and program |
-
2004
- 2004-03-31 JP JP2004101784A patent/JP4177779B2/en not_active Expired - Fee Related
-
2005
- 2005-03-25 US US11/089,225 patent/US9230184B2/en not_active Expired - Fee Related
- 2005-03-31 CN CNB2005100597009A patent/CN100365657C/en not_active Expired - Fee Related
Patent Citations (22)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5680481A (en) * | 1992-05-26 | 1997-10-21 | Ricoh Corporation | Facial feature extraction method and apparatus for a neural network acoustic and visual speech recognition system |
US5835616A (en) * | 1994-02-18 | 1998-11-10 | University Of Central Florida | Face detection using templates |
US5859921A (en) * | 1995-05-10 | 1999-01-12 | Mitsubishi Denki Kabushiki Kaisha | Apparatus for processing an image of a face |
US5878156A (en) * | 1995-07-28 | 1999-03-02 | Mitsubishi Denki Kabushiki Kaisha | Detection of the open/closed state of eyes based on analysis of relation between eye and eyebrow images in input face images |
US5774591A (en) * | 1995-12-15 | 1998-06-30 | Xerox Corporation | Apparatus and method for recognizing facial expressions and facial gestures in a sequence of images |
US5802220A (en) * | 1995-12-15 | 1998-09-01 | Xerox Corporation | Apparatus and method for tracking facial motion through a sequence of images |
US5982912A (en) * | 1996-03-18 | 1999-11-09 | Kabushiki Kaisha Toshiba | Person identification apparatus and method using concentric templates and feature point candidates |
US6246779B1 (en) * | 1997-12-12 | 2001-06-12 | Kabushiki Kaisha Toshiba | Gaze position detection apparatus and method |
US5973664A (en) * | 1998-03-19 | 1999-10-26 | Portrait Displays, Inc. | Parameterized image orientation for computer displays |
US6571002B1 (en) * | 1999-05-13 | 2003-05-27 | Mitsubishi Denki Kabushiki Kaisha | Eye open/close detection through correlation |
US6950535B2 (en) * | 2000-01-31 | 2005-09-27 | Mitsubishi Denki Kabushiki Kaisha | Image collecting device, image retrieving device, and image collecting and retrieving system |
US6671391B1 (en) * | 2000-05-26 | 2003-12-30 | Microsoft Corp. | Pose-adaptive face detection system and process |
US20020150280A1 (en) * | 2000-12-04 | 2002-10-17 | Pingshan Li | Face detection under varying rotation |
US20030108225A1 (en) * | 2001-12-12 | 2003-06-12 | Sony Corporation | System and method for effectively extracting facial feature information |
US7239726B2 (en) * | 2001-12-12 | 2007-07-03 | Sony Corporation | System and method for effectively extracting facial feature information |
US7158177B2 (en) * | 2002-04-04 | 2007-01-02 | Mitsubishi Electric Corporation | Apparatus for and method of synthesizing face image |
US20030190060A1 (en) * | 2002-04-09 | 2003-10-09 | Industrial Technology Research Institute | Method for locating face landmarks in an image |
US7120279B2 (en) * | 2003-01-30 | 2006-10-10 | Eastman Kodak Company | Method for face orientation determination in digital color images |
US7349558B2 (en) * | 2003-02-19 | 2008-03-25 | Konica Minolta Holdings, Inc. | Image processing method, image processing apparatus, storage medium and program |
US20050100195A1 (en) * | 2003-09-09 | 2005-05-12 | Fuji Photo Film Co., Ltd. | Apparatus, method, and program for discriminating subjects |
US20060078176A1 (en) * | 2004-10-08 | 2006-04-13 | Fujitsu Limited | Biometric information input device, biometric authentication device, biometric information processing method, and computer-readable recording medium recording biometric information processing program |
US20060222264A1 (en) * | 2005-03-31 | 2006-10-05 | Siemens Ag | Method for vertically orienting a face shown in a picture |
Cited By (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8116535B2 (en) | 2006-07-25 | 2012-02-14 | Fujifilm Corporation | Image trimming apparatus |
US20080025558A1 (en) * | 2006-07-25 | 2008-01-31 | Fujifilm Corporation | Image trimming apparatus |
US9042610B2 (en) | 2007-03-30 | 2015-05-26 | Casio Computer Co., Ltd. | Image pickup apparatus equipped with face-recognition function |
US8615112B2 (en) * | 2007-03-30 | 2013-12-24 | Casio Computer Co., Ltd. | Image pickup apparatus equipped with face-recognition function |
US20080240563A1 (en) * | 2007-03-30 | 2008-10-02 | Casio Computer Co., Ltd. | Image pickup apparatus equipped with face-recognition function |
US20090180004A1 (en) * | 2008-01-10 | 2009-07-16 | Nikon Corporation | Information displaying apparatus |
US8743259B2 (en) * | 2008-01-10 | 2014-06-03 | Nikon Corporation | Information displaying apparatus |
US8971613B2 (en) | 2010-07-07 | 2015-03-03 | Nec Corporation | Image processing learning device, image processing learning method, and image processing learning program |
US20120252410A1 (en) * | 2011-03-28 | 2012-10-04 | Htc Corporation | Systems and Methods for Gesture Lock Obfuscation |
US9514297B2 (en) * | 2011-03-28 | 2016-12-06 | Htc Corporation | Systems and methods for gesture lock obfuscation |
KR20140002540A (en) * | 2012-06-29 | 2014-01-08 | 지이 메디컬 시스템즈 글로발 테크놀러지 캄파니 엘엘씨 | Detection apparatus, apparatus for medical use, and program |
KR101593272B1 (en) | 2012-06-29 | 2016-02-11 | 지이 메디컬 시스템즈 글로발 테크놀러지 캄파니 엘엘씨 | Detection apparatus, apparatus for medical use, and program |
US10891019B2 (en) * | 2016-02-29 | 2021-01-12 | Huawei Technologies Co., Ltd. | Dynamic thumbnail selection for search results |
US20180018946A1 (en) * | 2016-07-12 | 2018-01-18 | Qualcomm Incorporated | Multiple orientation detection |
US10347218B2 (en) * | 2016-07-12 | 2019-07-09 | Qualcomm Incorporated | Multiple orientation detection |
Also Published As
Publication number | Publication date |
---|---|
CN100365657C (en) | 2008-01-30 |
CN1677441A (en) | 2005-10-05 |
JP2005285035A (en) | 2005-10-13 |
US9230184B2 (en) | 2016-01-05 |
JP4177779B2 (en) | 2008-11-05 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US9230184B2 (en) | Image display control apparatus and method, and program for controlling image display control apparatus | |
US7884874B2 (en) | Digital still camera and method of controlling same | |
US7561718B2 (en) | Image search apparatus for images to be detected, and method of controlling same | |
EP1785914B1 (en) | Image processing for object detection | |
US7801360B2 (en) | Target-image search apparatus, digital camera and methods of controlling same | |
US8077216B2 (en) | Image pickup apparatus with a human face detecting function, method and program product for detecting a human face | |
JP5256806B2 (en) | Target image detection method and image detection apparatus | |
US7893963B2 (en) | Digital camera which estimates and corrects small camera rotations | |
US7376347B2 (en) | Digital still camera, image reproducing apparatus, face image display apparatus and methods of controlling same | |
US7305146B2 (en) | Tilt correction of electronic images | |
JP5106142B2 (en) | Electronic camera | |
US7460782B2 (en) | Picture composition guide | |
JP5625995B2 (en) | Subject tracking device, subject tracking method and program | |
US20070286488A1 (en) | Image processing apparatus, image processsing method, and imaging apparatus | |
JP2006293782A (en) | Image processing device and image processing program | |
JP4894708B2 (en) | Imaging device | |
JP2004349750A (en) | Digital camera and control method therefor | |
JP2007265149A (en) | Image processor, image processing method and imaging device | |
JP2008181439A (en) | Face detection device and method, and imaging apparatus | |
US7956911B2 (en) | Digital photographing apparatus, and method and program for controlling the same | |
JP5740934B2 (en) | Subject detection apparatus, subject detection method, and program | |
US20210195119A1 (en) | Image processing apparatus, image capturing apparatus and image processing method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
AS | Assignment |
Owner name: FUJI PHOTO FILM CO., LTD., JAPAN Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:SUGIMOTO, MASAHIKO;REEL/FRAME:016432/0365 Effective date: 20050302 |
|
AS | Assignment |
Owner name: FUJI PHOTO FILM CO., LTD., JAPAN Free format text: CORRECTED COVER SHEET TO CORRECT ASSIGNEE ADDRESS, PREVIOUSLY RECORDED AT REEL/FRAME 016432/0365 (ASSIGNMENT OF ASSIGNOR'S INTEREST);ASSIGNOR:SUGIMOTO, MASAHIKO;REEL/FRAME:016970/0001 Effective date: 20050302 |
|
AS | Assignment |
Owner name: FUJIFILM HOLDINGS CORPORATION,JAPAN Free format text: CHANGE OF NAME;ASSIGNOR:FUJI PHOTO FILM CO., LTD.;REEL/FRAME:018875/0114 Effective date: 20061001 Owner name: FUJIFILM HOLDINGS CORPORATION, JAPAN Free format text: CHANGE OF NAME;ASSIGNOR:FUJI PHOTO FILM CO., LTD.;REEL/FRAME:018875/0114 Effective date: 20061001 |
|
AS | Assignment |
Owner name: FUJIFILM CORPORATION,JAPAN Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:FUJIFILM HOLDINGS CORPORATION;REEL/FRAME:018875/0838 Effective date: 20070130 Owner name: FUJIFILM CORPORATION, JAPAN Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:FUJIFILM HOLDINGS CORPORATION;REEL/FRAME:018875/0838 Effective date: 20070130 |
|
ZAAA | Notice of allowance and fees due |
Free format text: ORIGINAL CODE: NOA |
|
ZAAB | Notice of allowance mailed |
Free format text: ORIGINAL CODE: MN/=. |
|
ZAAA | Notice of allowance and fees due |
Free format text: ORIGINAL CODE: NOA |
|
ZAAB | Notice of allowance mailed |
Free format text: ORIGINAL CODE: MN/=. |
|
STCF | Information on status: patent grant |
Free format text: PATENTED CASE |
|
MAFP | Maintenance fee payment |
Free format text: PAYMENT OF MAINTENANCE FEE, 4TH YEAR, LARGE ENTITY (ORIGINAL EVENT CODE: M1551); ENTITY STATUS OF PATENT OWNER: LARGE ENTITY Year of fee payment: 4 |
|
FEPP | Fee payment procedure |
Free format text: MAINTENANCE FEE REMINDER MAILED (ORIGINAL EVENT CODE: REM.); ENTITY STATUS OF PATENT OWNER: LARGE ENTITY |
|
LAPS | Lapse for failure to pay maintenance fees |
Free format text: PATENT EXPIRED FOR FAILURE TO PAY MAINTENANCE FEES (ORIGINAL EVENT CODE: EXP.); ENTITY STATUS OF PATENT OWNER: LARGE ENTITY |
|
STCH | Information on status: patent discontinuation |
Free format text: PATENT EXPIRED DUE TO NONPAYMENT OF MAINTENANCE FEES UNDER 37 CFR 1.362 |
|
FP | Lapsed due to failure to pay maintenance fee |
Effective date: 20240105 |